Search Packages

mabwiser

[IJAIT 2021] MABWiser: Contextual Multi-Armed Bandits Library

tf-agents-nightly

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

vowpalwabbit

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

agents

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

tf-agents

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

contextualbandits

Python implementations of contextual bandits algorithms

pybandits

Python library for Multi-Armed Bandits

obp

Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation

banditml

A lightweight contextual bandit & reinforcement learning library designed to be used in production Python services.

mabalgs

:bust_in_silhouette: Multi-Armed Bandit Algorithms Library (MAB) :cop:

onn

Online Deep Learning: Learning Deep Neural Networks on the Fly / Non-linear Contextual Bandit Algorithm (ONN_THS)

catx

🐈‍⬛ Contextual bandits library for continuous action trees with smoothing in JAX

neuralbandit

Reproducing the experiments of the NeuralBandit and BanditForest papers.

improveai

Contextual Multi-Armed Bandit Platform for Scoring, Ranking & Decisions

sinapsis-vowpal-wabbit

Package for Vowpal Wabbit algorithms, featuring high-performance implementations of Contextual Bandits (ADF) and reinforcement learning patterns.

adaptive-shots

Few-shot prompting using Contextual Combinatorial Bandit optimizations

pyvw

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

contextual-bandits-algos

A library for contextual multi-armed bandit algorithms.

pulpo

WIP: A library and AWS sdk for non-contextual and contextual Multi-Armed-Bandit (MAB) algorithms for multiple use cases

vowpalwabbitds

Vowpal Wabbit Python package